1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
|
import docker
import re
import json
from datetime import datetime, timedelta
from collections import defaultdict, Counter
import matplotlib.pyplot as plt
import pandas as pd
class DockerLogAnalyzer:
def __init__(self):
self.client = docker.from_env()
def get_container_logs(self, container_name: str, hours: int = 24) -> list:
"""获取容器日志"""
try:
container = self.client.containers.get(container_name)
since = datetime.now() - timedelta(hours=hours)
logs = container.logs(
since=since,
timestamps=True,
stdout=True,
stderr=True
).decode('utf-8')
return logs.split('\n')
except Exception as e:
print(f"获取日志失败: {e}")
return []
def parse_log_levels(self, logs: list) -> dict:
"""解析日志级别分布"""
levels = Counter()
level_patterns = {
'ERROR': r'\b(ERROR|error|Error)\b',
'WARN': r'\b(WARN|warn|Warn|WARNING|warning|Warning)\b',
'INFO': r'\b(INFO|info|Info)\b',
'DEBUG': r'\b(DEBUG|debug|Debug)\b'
}
for log in logs:
for level, pattern in level_patterns.items():
if re.search(pattern, log):
levels[level] += 1
break
else:
levels['OTHER'] += 1
return dict(levels)
def find_error_patterns(self, logs: list) -> dict:
"""查找错误模式"""
error_patterns = defaultdict(int)
error_keywords = [
r'connection.*refused',
r'timeout',
r'out of memory',
r'permission denied',
r'file not found',
r'database.*error',
r'authentication.*failed',
r'ssl.*error'
]
for log in logs:
if re.search(r'\b(ERROR|error|Error)\b', log):
for pattern in error_keywords:
if re.search(pattern, log, re.IGNORECASE):
error_patterns[pattern] += 1
return dict(error_patterns)
def analyze_response_times(self, logs: list) -> dict:
"""分析响应时间"""
response_times = []
time_pattern = r'(\d+(?:\.\d+)?)\s*ms'
for log in logs:
matches = re.findall(time_pattern, log)
for match in matches:
response_times.append(float(match))
if response_times:
return {
'count': len(response_times),
'avg': sum(response_times) / len(response_times),
'min': min(response_times),
'max': max(response_times),
'p95': sorted(response_times)[int(len(response_times) * 0.95)]
}
return {}
def generate_report(self, container_name: str, hours: int = 24) -> dict:
"""生成分析报告"""
logs = self.get_container_logs(container_name, hours)
if not logs:
return {'error': '无法获取日志'}
report = {
'container': container_name,
'analysis_period': f'{hours} hours',
'total_logs': len(logs),
'log_levels': self.parse_log_levels(logs),
'error_patterns': self.find_error_patterns(logs),
'response_times': self.analyze_response_times(logs),
'timestamp': datetime.now().isoformat()
}
return report
def visualize_log_levels(self, report: dict):
"""可视化日志级别分布"""
levels = report['log_levels']
plt.figure(figsize=(10, 6))
plt.bar(levels.keys(), levels.values())
plt.title(f'Log Levels Distribution - {report["container"]}')
plt.xlabel('Log Level')
plt.ylabel('Count')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()
def export_report(self, report: dict, filename: str = None):
"""导出报告"""
if not filename:
filename = f"log_analysis_{report['container']}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
with open(filename, 'w', encoding='utf-8') as f:
json.dump(report, f, indent=2, ensure_ascii=False)
print(f"报告已导出到: {filename}")
analyzer = DockerLogAnalyzer()
report = analyzer.generate_report('my_app_container', hours=24)
print(json.dumps(report, indent=2))
|
